Increasing occupant localization precision through identification of footstep-contact dynamics
نویسندگان
چکیده
Information regarding occupants inside buildings has the potential to improve security, energy management, and caregiving. Typical sensing approaches for occupant localization rely on mobile devices cameras. These systems compromise privacy. Occupant using floor-vibration measurements, induced by footsteps, is a non-intrusive method that requires few sensors (one per ~35 m2). Current occupant-localization methodologies vibration measurements are data-driven techniques. techniques do not account structural behavior of floor slabs leading ambiguous interpretations vibrations measurement in presence obstructions varying rigidities. In this paper, model-based approach error-domain model falsification (EDMF) used overcome these limitations. EDMF incorporates information related physics-based models interpretation identify population possible locations. accommodates systematic errors bias reject contradict data. Uncertainties from multiple sources such as modeling imperfection walking-gait variability included explicitly while estimating locations EDMF. A unique footstep-contact dynamics proposed evaluated its ability precision localization. The involves dividing floor-slab into zones knowledge behavior. Clustering measured define several severity levels helps reduce uncertainty walking gait thus improving accuracy use loading input simulations. utility full-scale case study. Localization increased more than 50% compared with non-zone-based strategies.
منابع مشابه
Learning Vector Quantization in Footstep Identification
This paper reports experiments on recognizing walkers from measurements with a pressure-sensitive floor, more specifically, a floor covered with EMFi material. A 100 square meter pressure-sensitive floor (EMFi floor) was recently installed in the Intelligent Systems Group’s research laboratory at the University of Oulu as part of a smart living room. The floor senses the changes in the pressure...
متن کاملImproving Image-Based Localization through Increasing Correct Feature Correspondences
Image-based localization is to provide contextual information based on a query image. Current state-of-the-art methods use 3D Structure-from-Motion reconstruction model to aid in localizing the query image, either by 2D-to-3D matching or by 3D-to-2D matching. By adding camera pose estimation, the system can perform image localization more accurately. However, incorrect feature correspondences b...
متن کاملPediatric occupant-vehicle contact maps in rollover motor vehicle crashes.
OBJECTIVE Rollover crashes account for more than 33% of all motor vehicle-related fatalities and have the highest fatality risk of all crash types, at 1.37% in the United States. There is increased awareness of the high fatality rate associated with this crash type, but there is very limited pediatric-specific data related to rollover crashes in the United States. Recent focus on rollover mitig...
متن کاملFootstep Identification from Pressure Signals Using Hidden Markov Models
This paper reports initial experiments on recognizing walkers from measurements with a pressure-sensitive floor, more specifically, a floor covered with EMFi material. A 100 square meter pressure-sensitive floor (EMFi floor) was recently installed in the Intelligent Systems Group’s research laboratory at the University of Oulu as part of a smart living room. The floor senses the changes in the ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Advanced Engineering Informatics
سال: 2021
ISSN: ['1474-0346', '1873-5320']
DOI: https://doi.org/10.1016/j.aei.2021.101367